Yuankun Xie

Yuankun Xie

PhD candidate

Hi, I am Yuankun Xie, a final year Ph.D. candidate at the Communication University of China, and a joint Ph.D. student at the Institute of Automation, Chinese Academy of Sciences.

My research interests include audio deepfake detection, audio large language models (ALLMs), domain generalization, out-of-distribution detection, and neural audio codecs. I have published 20+ papers in top-tier international AI conferences and journals, including TIFS, AAAI, IJCAI, ICASSP, and INTERSPEECH.

I am seeking a research-oriented postdoctoral position starting in June 2026 (expected graduation date). My research interests lie in speech and audio processing, with a particular focus on audio/multimodal deepfake detection and audio large language models. I am also open to related research topics beyond those listed above within the broader area of speech and audio processing. If you have relevant opportunities, please feel free to contact me at xieyuankun@cuc.edu.cn.

🔥 Milestones

  • 2026.01:   🎉 2 papers accepted by ICASSP 2026.
  • 2025.11:   🎉 1 papers accepted by AAAI 2026.
  • 2025.11:   💻 Ranked 1st place in both Track 1 and Track 2 of the ESDD Competition.
  • 2025.07:   💻 Ranked 3rd in Track 3 of the Alibaba Tianchi 2025 Global AI Attack and Defense Challenge.
  • 2024.12:   🎉 1 journal papers accepted by TASLP.
  • 2024.09:   🌏 Attended INTERSPEECH 2024 in Greece, presenting one poster and one oral presentation.
  • 2024.08:   🎉 1 papers accepted by INTERSPEECH 2024W (ASVspoof2024).
  • 2024.08:   🎉 3 papers accepted by ISCSLP 2024.
  • 2024.06:   🎉 4 papers accepted by INTERSPEECH 2024.
  • 2024.04:   🌏 Attended ICASSP 2024 in Korea, presenting one poster and one oral presentation.
  • 2024.01:   🎉 2 papers accepted by ICASSP 2024.
  • 2023.11:   👓 Joined Professor Jianhua Tao’s group at the Institute of Automation for my Ph.D. joint training, under the specific guidance of Dr. Ruibo Fu.
  • 2023.10:   🎉 1 journal paper accepted by TIFS.
  • 2023.08:   🌏 Attended IJCAI 2023 DADA workshop (ADD2023) in Macao, delivering one presentation.
  • 2023.06:   🎉 2 papers accepted by INTERSPEECH 2023 and IJCAI 2023 DADA workshop.
  • 2023.05:   💻 Ranked 6 / 14 in Track 1.1, 5 / 52 in Track 1.2, and 6 / 17 in Track 2 of the ADD2023 Competition.
  • 2022.09:   👓 Joined Professor Long Ye’s group at the Communication University of China, under the specific guidance of Dr. Haonan Cheng.

📝 First-Author Publications

To learn more about my publications, please visit my Google Scholar page.

Journal

  • J2-TASLP 2025: The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio [paper][code]

    Yuankun Xie, Yi Lu, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Jianhua Tao, Xin Qi, Xiaopeng Wang, Yukun Liu, Haonan Cheng, Long Ye, Yi Sun

  • J1-TIFS 2024: Domain Generalization Via Aggregation and Separation for Audio Deepfake Detection [paper]

    Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye

Conference

  • C11-AAAI 2026 : Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception [paper][code]

    Yuankun Xie, Ruibo Fu, Zhiyong Wang, Xiaopeng Wang, Songjun Cao, Long Ma, Haonan Cheng, Long Ye

  • C10-ICASSP 2026 : Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform [paper]

    Yuankun Xie, Ruibo Fu, Xiaopeng Wang, Zhiyong Wang, Ya Li, Zhengqi Wen, Haonnan Cheng, Long Ye

  • C9-INTERSPEECH 2024W (ASVspoof2024): Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge [paper]

    Yuankun Xie, Xiaopeng Wang, Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Haonan Cheng, Long Ye

  • C8-ISCSLP 2024: Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio? [paper][code]

    Yuankun Xie, Chenxu Xiong, Xiaopeng Wang, Zhiyong Wang, Yi Lu, Xin Qi, Ruibo Fu, Yukun Liu, Zhengqi Wen, Jianhua Tao, et al.

  • C7-INTERSPEECH 2024: Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion strategy [paper][code]

    Yuankun Xie, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Xiaopeng Wang, Haonnan Cheng, Long Ye, Jianhua Tao

  • C6-INTERSPEECH 2024: Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio [paper][code]

    Yi Lu†, Yuankun Xie†, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Zhiyong Wang, Xin Qi, Xuefei Liu, Yongwei Li, Yukun Liu, et al.

  • C5-ICASSP 2024: An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection [paper][code]

    Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye

  • C4-ICASSP 2024: FSD: An initial chinese dataset for fake song detection [paper][code]

    Yuankun Xie, Jingjing Zhou, Xiaolin Lu, Zhenghao Jiang, Yuxin Yang, Haonan Cheng, Long Ye

  • C3-IJCAI 2023: Single domain generalization for audio deepfake detection [paper]

    Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye

  • C2-INTERSPEECH 2023: Learning A Self-Supervised Domain-Invariant Feature Representation for Generalized Audio Deepfake Detection [paper]

    Yuankun Xie, Haonan Cheng, Yutian Wang, Long Ye

  • C1-ICME 2023: Unsupervised quantized prosody representation for controllable speech synthesis [paper]

    Yutian Wang†, Yuankun Xie†, Kun Zhao, Hui Wang, Qin Zhang

🏢 Industrial Experiences

  • 2024.11 - 2025.4 Research Intern, Tencent YouTu Lab (Beijing, China)
    • (ICASSP26) Focused on audio deepfake detection on social media platform.
    • (Neurocomputing) Open-set neural codec source tracing and explainable ALM-based deepfake audio detection.
    • (AAAI26) Developed universally cross-type audio deepfake coutermeasure (including speech, sound, singing voice, and music).

  • 2025.6 - 2025.8 Research Intern, ByteDance (Beijing, China)

    • Focused on the task of synthesizing first-order ambisonic spatial audio from 360-degree video and spatial audio captions.

  • 2025.10 - now Research Intern, Ant Group (Beijing, China)

    • (ACL26 submitted) Focused on Interpretable All-Type Audio Deepfake Detection with Audio LLMs.

💻 Competition

🌏 Visitor Map